You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by go...@apache.org on 2015/05/29 02:50:26 UTC
[19/82] [abbrv] hive git commit: HIVE-8769 : Physical optimizer :
Incorrect CE results in a shuffle join instead of a Map join (PK/FK pattern
not detected) (Pengcheng Xiong via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union23.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union23.q.out b/ql/src/test/results/clientpositive/spark/union23.q.out
index dda7234..2b114fc 100644
--- a/ql/src/test/results/clientpositive/spark/union23.q.out
+++ b/ql/src/test/results/clientpositive/spark/union23.q.out
@@ -31,28 +31,35 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Transform Operator
command: cat
output info:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Map 3
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union24.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union24.q.out b/ql/src/test/results/clientpositive/spark/union24.q.out
index 22ec159..7a05198 100644
--- a/ql/src/test/results/clientpositive/spark/union24.q.out
+++ b/ql/src/test/results/clientpositive/spark/union24.q.out
@@ -194,18 +194,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src2
+ Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -274,18 +278,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src3
+ Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -354,18 +362,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src4
+ Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -511,11 +523,13 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 51 Data size: 244 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -736,18 +750,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src2
+ Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 319 Data size: 1531 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -816,18 +834,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src3
+ Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 319 Data size: 1531 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1032,14 +1054,17 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
outputColumnNames: _col0, _col6
+ Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col6 (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 319 Data size: 1531 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1255,18 +1280,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src2
+ Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 262 Data size: 1257 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1335,18 +1364,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src3
+ Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 262 Data size: 1257 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1576,11 +1609,13 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 56 Data size: 269 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 262 Data size: 1257 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union25.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union25.q.out b/ql/src/test/results/clientpositive/spark/union25.q.out
index 67416a3..db7dfc5 100644
--- a/ql/src/test/results/clientpositive/spark/union25.q.out
+++ b/ql/src/test/results/clientpositive/spark/union25.q.out
@@ -74,55 +74,69 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Map 3
Map Operator Tree:
TableScan
alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Map 5
Map Operator Tree:
TableScan
alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Group By Operator
@@ -149,18 +163,22 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union26.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union26.q.out b/ql/src/test/results/clientpositive/spark/union26.q.out
index fa996ed..42d4260 100644
--- a/ql/src/test/results/clientpositive/spark/union26.q.out
+++ b/ql/src/test/results/clientpositive/spark/union26.q.out
@@ -89,44 +89,57 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Lateral View Forward
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Lateral View Join Operator
outputColumnNames: _col0, _col1, _col7
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Select Operator
expressions: array(1,2,3) (type: array<int>)
outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
UDTF Operator
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col1, _col7
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Reducer 2
Reduce Operator Tree:
@@ -134,15 +147,18 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Reducer 3
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union27.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union27.q.out b/ql/src/test/results/clientpositive/spark/union27.q.out
index e66db27..543eade 100644
--- a/ql/src/test/results/clientpositive/spark/union27.q.out
+++ b/ql/src/test/results/clientpositive/spark/union27.q.out
@@ -49,29 +49,37 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: dim_pho
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 97) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: value (type: string)
outputColumnNames: _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: '97' (type: string)
sort order: +
Map-reduce partition columns: '97' (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Map 3
Map Operator Tree:
TableScan
alias: jackson_sev_add
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 97) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: value (type: string)
outputColumnNames: _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: '97' (type: string)
sort order: +
Map-reduce partition columns: '97' (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Map 4
Map Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union28.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union28.q.out b/ql/src/test/results/clientpositive/spark/union28.q.out
index 0294bad..5160879 100644
--- a/ql/src/test/results/clientpositive/spark/union28.q.out
+++ b/ql/src/test/results/clientpositive/spark/union28.q.out
@@ -49,14 +49,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -111,17 +115,22 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -134,17 +143,22 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union29.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union29.q.out b/ql/src/test/results/clientpositive/spark/union29.q.out
index daa581f..1776b4d 100644
--- a/ql/src/test/results/clientpositive/spark/union29.q.out
+++ b/ql/src/test/results/clientpositive/spark/union29.q.out
@@ -46,14 +46,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -63,14 +67,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -80,14 +88,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union3.q.out b/ql/src/test/results/clientpositive/spark/union3.q.out
index 25e78e3..834b6d4 100644
--- a/ql/src/test/results/clientpositive/spark/union3.q.out
+++ b/ql/src/test/results/clientpositive/spark/union3.q.out
@@ -107,13 +107,16 @@ STAGE PLANS:
Reduce Operator Tree:
Limit
Number of rows: 1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Select Operator
expressions: 1 (type: int)
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Reducer 3
Reduce Operator Tree:
Select Operator
@@ -131,35 +134,44 @@ STAGE PLANS:
Reduce Operator Tree:
Limit
Number of rows: 1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Select Operator
expressions: 2 (type: int)
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Reducer 7
Reduce Operator Tree:
Limit
Number of rows: 1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Select Operator
expressions: 3 (type: int)
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Reducer 9
Reduce Operator Tree:
Limit
Number of rows: 1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Select Operator
expressions: 4 (type: int)
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union30.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union30.q.out b/ql/src/test/results/clientpositive/spark/union30.q.out
index b9b59d4..a81417d 100644
--- a/ql/src/test/results/clientpositive/spark/union30.q.out
+++ b/ql/src/test/results/clientpositive/spark/union30.q.out
@@ -63,14 +63,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -122,14 +126,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -142,17 +150,22 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -165,17 +178,22 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union31.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union31.q.out b/ql/src/test/results/clientpositive/spark/union31.q.out
index d58d17c..4482b95 100644
--- a/ql/src/test/results/clientpositive/spark/union31.q.out
+++ b/ql/src/test/results/clientpositive/spark/union31.q.out
@@ -87,81 +87,101 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Map 6
Map Operator Tree:
TableScan
alias: t1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col1
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Map 7
Map Operator Tree:
TableScan
alias: t2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Map 8
Map Operator Tree:
TableScan
alias: t2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col1
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 2
Reduce Operator Tree:
@@ -395,10 +415,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 3
Reduce Operator Tree:
@@ -447,10 +469,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Stage: Stage-0
@@ -657,16 +681,20 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t2
+ Statistics: Num rows: 6 Data size: 18 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 6 Data size: 18 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Group By Operator
@@ -674,16 +702,20 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Reducer 3
Reduce Operator Tree:
Forward
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union32.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union32.q.out b/ql/src/test/results/clientpositive/spark/union32.q.out
index c8909a5..443796c 100644
--- a/ql/src/test/results/clientpositive/spark/union32.q.out
+++ b/ql/src/test/results/clientpositive/spark/union32.q.out
@@ -59,22 +59,28 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(key) (type: double)
outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Map 3
Map Operator Tree:
TableScan
alias: t2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(UDFToLong(key)) (type: double)
outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
+ Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Select Operator
@@ -186,11 +192,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(key) (type: double)
outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -201,11 +210,14 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(UDFToLong(_col0)) (type: double)
outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -294,11 +306,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(key) (type: double)
outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -335,11 +350,14 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(UDFToLong(_col0)) (type: double)
outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -454,11 +472,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(key) (type: double), key (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -469,11 +490,14 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
outputColumnNames: _col0, _col5
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(UDFToLong(_col0)) (type: double), UDFToString(UDFToDouble(_col5)) (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -562,11 +586,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -603,11 +630,14 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
outputColumnNames: _col0, _col5
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToDouble(UDFToLong(_col0)) (type: double), UDFToDouble(_col5) (type: double)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union33.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union33.q.out b/ql/src/test/results/clientpositive/spark/union33.q.out
index 2de2984..680a627 100644
--- a/ql/src/test/results/clientpositive/spark/union33.q.out
+++ b/ql/src/test/results/clientpositive/spark/union33.q.out
@@ -49,13 +49,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 0) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: '0' (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -103,11 +107,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), UDFToString(_col1) (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -216,13 +223,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 0) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: '0' (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -249,11 +260,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), UDFToString(_col1) (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union34.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union34.q.out b/ql/src/test/results/clientpositive/spark/union34.q.out
index d5e7e4a..a9edf14 100644
--- a/ql/src/test/results/clientpositive/spark/union34.q.out
+++ b/ql/src/test/results/clientpositive/spark/union34.q.out
@@ -88,18 +88,18 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 3
Map Operator Tree:
TableScan
- alias: src10_1
- Statistics: Num rows: 0 Data size: 114 Basic stats: PARTIAL Column stats: NONE
+ alias: src10_2
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
@@ -110,18 +110,21 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 3 <- Map 2 (SORT, 1), Map 4 (SORT, 1), Map 5 (SORT, 1)
+ Reducer 2 <- Map 1 (SORT, 1), Map 4 (SORT, 1), Map 5 (SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
- alias: src10_2
+ alias: src10_1
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -130,10 +133,12 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col0, _col1
input vertices:
- 0 Map 1
+ 1 Map 3
+ Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Local Work:
Map Reduce Local Work
@@ -141,33 +146,39 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src10_3
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Map 5
Map Operator Tree:
TableScan
alias: src10_4
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Reducer 3
+ Reducer 2
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -269,19 +280,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src10_1
- Statistics: Num rows: 0 Data size: 114 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Map 4
Map Operator Tree:
@@ -304,23 +315,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src10_3
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Map 6
Map Operator Tree:
TableScan
alias: src10_4
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
@@ -328,19 +345,21 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reducer 3
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 353 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union4.q.out b/ql/src/test/results/clientpositive/spark/union4.q.out
index a7308ec..cdda727 100644
--- a/ql/src/test/results/clientpositive/spark/union4.q.out
+++ b/ql/src/test/results/clientpositive/spark/union4.q.out
@@ -79,14 +79,18 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'tst1' (type: string), _col0 (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
+ Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -98,14 +102,18 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'tst2' (type: string), _col0 (type: bigint)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
+ Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/d823fc80/ql/src/test/results/clientpositive/spark/union5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union5.q.out b/ql/src/test/results/clientpositive/spark/union5.q.out
index f8cd94b..a65c4e8 100644
--- a/ql/src/test/results/clientpositive/spark/union5.q.out
+++ b/ql/src/test/results/clientpositive/spark/union5.q.out
@@ -65,21 +65,26 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'tst1' (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 3
Reduce Operator Tree:
@@ -88,10 +93,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -102,21 +107,26 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'tst2' (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Stage: Stage-0
@@ -137,5 +147,5 @@ POSTHOOK: query: select unionsrc.key, count(1) FROM (select 'tst1' as key, count
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
#### A masked pattern was here ####
-tst2 1
tst1 1
+tst2 1